Heading to #EMNLP2026 in Budapest 🇭🇺? Check out our Oral paper, UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models!
🤔 UMMs unify understanding and generation. But are their text and images truly aligned?
💡 Our finding: UMMs usually get the reasoning right, but the image often doesn't follow it. Even more surprising: if we drop the reasoning and give the model only the final prompt it wrote itself, every model we tested does better, by a large margin.
📍 Oral Session 2 · Oct 25, 11:00–12:30 · Room G13-14
👇
Excited to share our work InfoEdit at EMNLP 2026! We study a simple but challenging question: can AI edit structured visuals while correctly handling layout reflow? 📊
🚀 Thrilled to introduce our work InfoEdit: Probing Global Layout Reasoning in Infographic Editing (EMNLP 2026).
AI can now help us generate posters, infographics and slides, through image generation (Nano Banana) or code generation (Codex).
🤔But can AI faithfully edit them, whether through image editing or multimodal code editing? When editing, one change forces the whole layout to adapt. We call this reflow, and we built InfoEdit to put it to the test.
🧩 What is reflow?
Take a simple edit: insert one new step into a cycle diagram. It sounds like adding one box. But a correct edit moves every node, reroutes every arrow, and rebalances the spacing, all while keeping existing content intact.
📊 InfoEdit at a glance
• 1,000 infographics, in HTML and PowerPoint
• 8 logical-relation families
• 4,000 editing instructions
• 4 tasks: Expand-Text · Insert-Element · Swap-Block · Reshape-Canvas
😬 Image editors struggle
Across 8 frontier image editors, only GPT-Image-2 clears 60% average success; most fall below 7%. Swap-Block is the hardest: even when we mark the exact blocks to swap, no editor exceeds 35%. The bottleneck isn't finding the target. It's reflow.
🖼️ vs 💻 Pixels or code?
Editing the HTML/PPT source instead, Kimi-K3 reaches 67.9% average success, above GPT-Image-2's 62.0%, and lifts Swap-Block from 25.5% → 62.8% Yet pixel-level editing still wins on Expand-Text and Reshape-Canvas. The two paradigms are complementary.
💡 Takeaway
Editing structured visuals isn't just changing the requested edits. It takes reasoning about how the whole design should adapt.
#EMNLP #multimodal #coding #imagediting
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow